{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:17Z","timestamp":1777865297073,"version":"3.51.4"},"reference-count":64,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFE0203100"],"award-info":[{"award-number":["2024YFE0203100"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476293"],"award-info":[{"award-number":["62476293"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00751","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"8011-8021","source":"Crossref","is-referenced-by-count":0,"title":["RoboTron-Drive: All-in-One Large Multimodal Model for Autonomous Driving"],"prefix":"10.1109","author":[{"given":"Zhijian","family":"Huang","sequence":"first","affiliation":[{"name":"Shenzhen Campus of Sun Yat-sen University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengjian","family":"Feng","sequence":"additional","affiliation":[{"name":"Meituan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Yan","sequence":"additional","affiliation":[{"name":"Meituan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baihui","family":"Xiao","sequence":"additional","affiliation":[{"name":"Meituan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zequn","family":"Jie","sequence":"additional","affiliation":[{"name":"Meituan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujie","family":"Zhong","sequence":"additional","affiliation":[{"name":"Meituan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaodan","family":"Liang","sequence":"additional","affiliation":[{"name":"Shenzhen Campus of Sun Yat-sen University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lin","family":"Ma","sequence":"additional","affiliation":[{"name":"Meituan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref2","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02061"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3435937"},{"key":"ref6","article-title":"Timemarker: A versatile video-llm for long and short video understanding with superior temporal localization ability","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3597926.3598072"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00101"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3259322"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01297"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01712"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00324"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72764-1_5"},{"key":"ref15","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref16","article-title":"Emma: End-to-end multimodal model for autonomous driving","author":"Hwang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00766"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_35"},{"key":"ref19","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref20","article-title":"Driving with internvl","author":"Li","journal-title":"2024. 2"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1167"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01806"},{"key":"ref23","article-title":"Automated evaluation of large visionlanguage models on self-driving corner cases","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref25","article-title":"Robouniview: Visual-language model with unified view representation for robotic manipulation","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref27","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"NeurIPS, 36"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2019.8917081"},{"key":"ref29","article-title":"Let\u2019s learn step by step: Enhancing in-context learning ability with curriculum learning","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680665"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72995-9_23"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00110"},{"key":"ref33","article-title":"Gpt-driver: Learning to drive with gpt","author":"Mao","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref34","article-title":"Gpt-driver: Learning to drive with gpt","author":"Mao","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref35","article-title":"A language agent for autonomous driving","author":"Mao","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref36","article-title":"Lingoqa: Video question answering for autonomous driving","author":"Marcu","year":"2024","journal-title":"ECCV"},{"key":"ref37","article-title":"Introducing llama 3.1: Our most capable models to date","year":"2024","journal-title":"Meta AI Blog"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.trf.2019.04.010"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_17"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01398"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00107"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28253"},{"key":"ref43","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume":"35","author":"Schuhmann","year":"2022","journal-title":"NeurIPS"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01432"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00852"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72943-0_15"},{"key":"ref48","article-title":"Drivevlm: The convergence of autonomous driving and large vision-language models","author":"Tian","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref49","article-title":"Bevgpt: Generative pre-trained large model for autonomous driving prediction, decision-making, and planning","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref50","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref51","article-title":"Omnidrive: A holistic llm-agent framework for autonomous driving with 3d perception, reasoning and planning","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref52","article-title":"Drivemlm: Aligning multi-modal large language models with behavioral planning states for autonomous driving","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref53","article-title":"Dilu: A knowledge-driven approach to autonomous driving with large language models","author":"Wen","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00621"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00954"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3440097"},{"key":"ref57","article-title":"Robomm: All-in-one multimodal large model for robotic manipulation","author":"Yan","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref58","article-title":"A survey of large language models for autonomous driving","author":"Yang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02039"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1117\/12.2679455"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3748302"},{"key":"ref63","article-title":"P3nav: A unified framework for embodied navigation integrating perception, planning, and prediction","author":"Zhong","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_8"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444570.pdf?arnumber=11444570","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:12:17Z","timestamp":1777529537000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444570\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00751","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}